Results 121 to 130 of about 36,247 (313)
An Explainable Scheme for Memorization of Noisy Instances by Downstream Evaluation
Applied SciencesDeep learning models are often perceived as black boxes, making it challenging to analyze the causal relationships between inputs and outputs. For this reason, the explainability of model learning has garnered increasing attention in recent years.
Chun-Yi Tsai +2 more
doaj +1 more source
Understanding and Explaining [PDF]
Almagest, 2012 The quest to provide a fundamental understanding and explanation of reality is an ambitious one. Perhaps it is too ambitious. The possible restrictions for such an enterprise to be successful must be inquired in order to determine the issue. Section 1 explores one’s understanding in reaching (scientific) conclusions: to what extent does a successful ...
openaire +3 more sources
Design and analysis strategies for robust microbiome ageing research
FEBS Letters, EarlyView.The gut microbiome changes with age and associates with age‐related morbidity and mortality, establishing it as a potential biomarker and intervention target for ageing. Realising this potential requires methodological rigour, yet distinguishing biological signals from methodological artefacts remains challenging across cohorts. This review provides an
Mark Olenik +5 more
wiley +1 more source
LCNN: Lightweight CNN Architecture for Software Defect Feature Identification Using Explainable AI
IEEE AccessSoftware defect identification (SDI) is a key part of improving the quality of software projects and lowering the risks that along with maintenance. It does identify the software defect causes that have not been reached yet to get sufficient results.
Momotaz Begum +7 more
doaj +1 more source
FEBS Letters, EarlyView.Protein aggregates threaten proteostasis and cell health. In human cells, Hsp70–J‐domain protein‐based disaggregases remove aggregates, but how they assemble remains unclear. Our biochemical findings show that DNAJA2‐ and DNAJB1‐containing disaggregase scaffolds enhance luciferase aggregate targeting, and that Hsp70 recruitment by both J‐domain ...
Anna Szlachcic, Nadinath B. Nillegoda
wiley +1 more source
Explainability is a leading solution offered to address the challenge of AI’s black boxing. However, a lot can go wrong when trying to apply explainability, and its success is far from certain. Moreover, there is insufficient empirical data regarding the
Sandøe, Peter +16 more
core +1 more source
Exploring explainability methods for graph neural networks
, 2022 With the growing use of deep learning methods, particularly graph neural networks, which encode intricate interconnectedness information, for a variety of real tasks, there is a necessity for explainability in such settings. In this paper, we demonstrate
core
A Study Comparing Explainability Methods: A Medical User Perspective
Acta Electrotechnica et InformaticaIn recent years, we have witnessed the rapid development of artificial intelligence systems and their presence in various fields. These systems are very efficient and powerful, but often unclear and insufficiently transparent.
Matejová Miroslava +2 more
doaj +1 more source
How is ʻUnexplainable’ and Non-transparent AI Affecting Healthcare Delivery?
Oslo Law ReviewThe healthcare industry is undergoing a profound transformation with the integration of artificial intelligence (AI) into various healthcare settings.
Vera Lúcia Raposo
doaj +1 more source
Reconstructing enzyme evolution by protein engineering
FEBS Letters, EarlyView.Natural enzyme evolution can be retraced by protein engineering methods such as directed evolution, rational design, and ancestral sequence reconstruction. These approaches reveal how enzymes emerged from ligand‐binding scaffolds, developed varying substrate preferences, formed oligomeric complexes, adapted to environmental changes, and evolved novel ...
Lukas Drexler +2 more
wiley +1 more source